Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.22431 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910007106207744 |
|---|---|
| author | Chen, Zhengyu Meng, Zhaoyi Zhao, Wenxiang Wang, Wansen Huang, Wenchao Cui, Jie Zhong, Hong Xiong, Yan |
| author_facet | Chen, Zhengyu Meng, Zhaoyi Zhao, Wenxiang Wang, Wansen Huang, Wenchao Cui, Jie Zhong, Hong Xiong, Yan |
| contents | Automatically reproducing Android app crashes from textual bug reports is challenging, particularly when the reports are incomplete and the modern UI exhibits high combinatorial complexity. Existing approaches based solely on reinforcement learning or large language models (LLMs) exhibit limitations in such scenarios. They struggle to infer unobserved steps and reconstruct the underlying user action sequences to navigate the vast UI interaction space, primarily due to limited goal-directed reasoning and planning. We present TreeMind, a novel technique that integrates LLMs with an adapted Monte Carlo Tree Search (MCTS) algorithm to achieve strategic UI exploration in bug reproduction. To the best of our knowledge, this is the first work to combine external decision-making with LLM semantic reasoning for reliable and accurate reproduction processes. We formulate the reproduction task as a target-driven search problem, leveraging MCTS as the core planning mechanism to iteratively refine action sequences. To enhance MCTS with semantic reasoning, we introduce two LLM-guided agents with distinct roles: Expander generates top-k promising actions based on the current UI state and exploration history, while Simulator estimates the likelihood that each candidate action leads toward successful reproduction by additionally leveraging dynamic environment feedback. By incorporating multi-modal UI inputs and tailored prompting strategies, TreeMind performs feedback-aware navigation that identifies essential user actions and incrementally reconstructs reproduction paths. We evaluate TreeMind on a dataset of 93 real-world Android bug reports from three widely-used benchmarks. Experimental results show that it significantly outperforms four state-of-the-art baselines, including ReBL, ReActDroid, AdbGPT, and ReproBot, in reproduction success rate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22431 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TreeMind: Automatically Reproducing Android Bug Reports via LLM-empowered Monte Carlo Tree Search Chen, Zhengyu Meng, Zhaoyi Zhao, Wenxiang Wang, Wansen Huang, Wenchao Cui, Jie Zhong, Hong Xiong, Yan Software Engineering Automatically reproducing Android app crashes from textual bug reports is challenging, particularly when the reports are incomplete and the modern UI exhibits high combinatorial complexity. Existing approaches based solely on reinforcement learning or large language models (LLMs) exhibit limitations in such scenarios. They struggle to infer unobserved steps and reconstruct the underlying user action sequences to navigate the vast UI interaction space, primarily due to limited goal-directed reasoning and planning. We present TreeMind, a novel technique that integrates LLMs with an adapted Monte Carlo Tree Search (MCTS) algorithm to achieve strategic UI exploration in bug reproduction. To the best of our knowledge, this is the first work to combine external decision-making with LLM semantic reasoning for reliable and accurate reproduction processes. We formulate the reproduction task as a target-driven search problem, leveraging MCTS as the core planning mechanism to iteratively refine action sequences. To enhance MCTS with semantic reasoning, we introduce two LLM-guided agents with distinct roles: Expander generates top-k promising actions based on the current UI state and exploration history, while Simulator estimates the likelihood that each candidate action leads toward successful reproduction by additionally leveraging dynamic environment feedback. By incorporating multi-modal UI inputs and tailored prompting strategies, TreeMind performs feedback-aware navigation that identifies essential user actions and incrementally reconstructs reproduction paths. We evaluate TreeMind on a dataset of 93 real-world Android bug reports from three widely-used benchmarks. Experimental results show that it significantly outperforms four state-of-the-art baselines, including ReBL, ReActDroid, AdbGPT, and ReproBot, in reproduction success rate. |
| title | TreeMind: Automatically Reproducing Android Bug Reports via LLM-empowered Monte Carlo Tree Search |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2509.22431 |